检索结果-内蒙古大学图书馆

AI-driven 3D Spatial Transcriptomics

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Almagro-Pérez, Cristina Song, Andrew H. Weishaupt, Luca Kim, Ahrong Jaume, Guillaume Williamson, Drew F.K. Hemker, Konstantin Lu, Ming Y. Singh, Kritika Chen, Bowen Le, Long Phi Baras, Alexander S. Jiang, Sizun Bashashati, Ali Liu, Jonathan T.C. Mahmood, Faisal Department of Pathology Mass General Brigham Harvard Medical School BostonMA United States Cancer Program Broad Institute of Harvard and MIT CambridgeMA United States Data Science Program Dana-Farber Cancer Institute BostonMA United States Harvard-MIT Division of Health Sciences and Technology Massachusetts Institute of Technology CambridgeMA United States Department of Pathology Pusan National University Busan Korea Republic of Department of Pathology and Laboratory Medicine Emory University School of Medicine AtlantaGA United States Department of Computer Science & Technology University of Cambridge Cambridge United Kingdom Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology CambridgeMA United States Rutgers Robert Wood Johnson Medical School New BrunswickNJ United States Department of Pathology Johns Hopkins Hospital BaltimoreMD United States Department of Biomedical Engineering Johns Hopkins Hospital BaltimoreMD United States Broad Institute of Harvard and MIT CambridgeMA United States Center for Virology and Vaccine Research Beth Israel Deaconess Medical Center Harvard Medical School BostonMA United States Department of Pathology Dana Farber Cancer Institute BostonMA United States Department of Pathology and Laboratory Medicine University of British Columbia VancouverBC Canada School of Biomedical Engineering University of British Columbia VancouverBC Canada Department of Mechanical Engineering Bioengineering Laboratory Medicine & Pathology University of Washington SeattleWA United States Harvard Data Science Initiative Harvard University CambridgeMA United States

A comprehensive three-dimensional (3D) map of tissue architecture and gene expression is crucial for illuminating the complexity and heterogeneity of tissues across diverse biomedical applications1. However, most spatial transcriptomics (ST) approaches remain limited to two-dimensional (2D) sections of tissue2–4. Although current 3D ST methods hold promise, they typically require extensive tissue sectioning, are complex, are not compatible with non-destructive 3D tissue imaging technologies, and often lack scalability5–8. Here, we present VOlumetrically Resolved Transcriptomics EXpression (VORTEX), an AI framework that leverages 3D tissue morphology and minimal 2D ST to predict volumetric 3D ST. By pretraining on diverse 3D morphology–transcriptomic pairs from heterogeneous tissue samples and then fine-tuning on minimal 2D ST data from a specific volume of interest, VORTEX learns both generic tissue-related and sample-specific morphological correlates of gene expression. This approach enables dense, high-throughput, and fast 3D ST, scaling seamlessly to large tissue volumes far beyond the reach of existing 3D ST techniques. By offering a cost-effective and minimally destructive route to obtaining volumetric molecular insights, we anticipate that VORTEX will accelerate biomarker discovery and our understanding of morphomolecular associations and cell states in complex tissues. Interactive 3D ST volumes can be viewed at https://***/. © 2025, CC BY-NC-ND.

关键词： Vortex flow

Brain oscillatory activity evoked by chirp modulated tones in healthy children

学校读者我要写书评

暂无评论

Heliyon 2024年第24期10卷 e40599页

作者： Irazabal, Nadia Inés Urrestarazu, Elena Valencia, Miguel Manzanilla, Oscar Crespo-Eguilaz, Nerea Isaguirre, María Belén Sánchez-Carpintero, Rocío Paediatric Neurology Unit. Department of Paediatrics. Clinica Universidad de Navarra Pamplona Spain Department of Clinical Neurophysiology. Clinica Universidad de Navarra Pamplona Spain Biomedical Engineering Program Universidad de Navarra CIMA Pamplona Spain IdiSNA Instituto de Investigación Sanitaria de Navarra Pamplona Spain Institute of Data Science and Artificial Intelligence Universidad de Navarra Pamplona Spain Statistical Consultant Argentina

Aim: To describe the features of cortical oscillatory activity and neuronal synchronization by monitoring responses evoked by chirp-modulated tone (CMT) and look for relationships with cognition in healthy children. Methods: We recruited 23 healthy children, 1–18 years old, assessed their cognitive abilities and recorded the cortical oscillatory activity evoked by CMTs. We obtained descriptive statistics and looked for correlations with cognitive abilities. Results: In the low gamma band, the neuronal synchronization evoked by CMTs increased with age, reaching adult features by 12 years of age (rho = 0.5;p = 0.042). In the high gamma band, neuronal recruitment was greater at younger ages (rho = −0.55;p = 0.029). In four of the six under-6-year-old participants, there was no CMT-evoked response. We found that the greater a child's receptive vocabulary skills, the lower the frequency at which maximal neuronal recruitment occurred (rho = −0.65;p = 0.003). Interpretation: CMT-evoked cortical oscillatory activity is affected by degree of brain maturation and could be a potential biomarker of language-related disability. Our description of the cortical responses evoked by CMTs in healthy children is a step towards recognition of abnormal patterns and the possible use of this approach as a biomarker of brain disorders in children. © 2024 The Authors

关键词： Brain maturation Brain oscillatory activity Chirp Healthy children Neurodevelopment biomarker

Tempered enthusiasm by interviewed experts for synthetic data and ELSI checklists for AI in medicine

学校读者我要写书评

暂无评论

AI and ethics 2025年第3期5卷 3241-3254页

作者： Laura Y Cabrera Jennifer Wagner Sara Gerke Daniel Susser Department of Engineering Science and Mechanics Pennsylvania State University W-316 Millennium Science Complex University Park PA 16802 USA. Department of Philosophy Pennsylvania State University University Park PA 16802 USA. Huck Institutes of the Life Sciences Pennsylvania State University University Park PA 16802 USA. Rock Ethics Institute Pennsylvania State University University Park PA 16802 USA. Bioethics Program Pennsylvania State University University Park PA 16802 USA. School of Engineering Design and Innovation Pennsylvania State University University Park PA 16802 USA. Department of Anthropology Pennsylvania State University University Park PA 16802 USA. Department of Biomedical Engineering Pennsylvania State University University Park PA 16802 USA. Institute for Computational and Data Sciences Pennsylvania State University University Park PA 16802 USA. College of Law and European Union Center University of Illinois Urbana-Champaign Champaign IL 61820 USA. Department of Information Science Cornell University Ithaca NY 14853 USA.

Synthetic data are increasingly being used in data-driven fields. While synthetic data is a promising tool in medicine, it raises new ethical, legal, and social implications (ELSI) challenges. There is a recognized need for well-designed approaches and standards for documenting and communicating relevant information about artificial intelligence (AI) research datasets and models, including consideration of the many ELSI challenges. This study investigates the ethical dimensions of synthetic data and explores the utility and challenges of ELSI-focused computational checklists for biomedical AI via semi-structure interviews with subject matter experts. Our results suggest that AI experts have tempered views about the promises and challenges of both synthetic data and ELSI-focused computational checklists. Experts discussed a number of ELSI issues covered by previous literature on the topic, such as issues of bias and privacy, yet other less discussed ELSI issues, such as social justice implications and issues of trust were also raised. When discussing ELSI-focused computational checklists our participants highlighted the challenges connected to developing and implementing them.

关键词： Artificial intelligence Computational checklists ELSI Synthetic data

Cortical network reconfiguration aligns with shifts of basal ganglia and cerebellar influence

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Nestor, Kimberly Rasero, Javier Betzel, Richard Gianaros, Peter J. Verstynen, Timothy Department of Psychology Carnegie Mellon University PittsburghPA United States Center for the Neural Basis of Cognition PittsburghPA United States Carnegie Mellon Neuroscience Institute PittsburghPA United States Department of Biomedical Engineering Carnegie Mellon University PittsburghPA United States School of Data Science University of Virginia CharlottesvilleVA United States Department of Psychological and Brain Sciences Indiana University BloomingtonIN United States Cognitive Science Program Indiana University BloomingtonIN United States Indiana University Network Science Institute BloomingtonIN United States Department of Neuroscience University of Minnesota MinneapolisMN55455 United States Department of Psychology University of Pittsburgh PittsburghPA United States

Mammalian functional architecture flexibly adapts, transitioning from integration where information is distributed across the cortex, to segregation where information is focal in densely connected communities of brain regions. This flexibility in cortical brain networks is hypothesized to be driven by control signals originating from subcortical pathways, with the basal ganglia shifting the cortex towards integrated processing states and the cerebellum towards segregated states. In a sample of healthy human participants (N=242), we used fMRI to measure temporal variation in global brain networks while participants performed two tasks with similar cognitive demands (Stroop and Multi-Source Inference Task (MSIT)). Using the modularity index, we determined cortical networks shifted from integration (low modularity) at rest to high modularity during easier i.e. congruent (segregation). Increased task difficulty (incongruent) resulted in lower modularity in comparison to the easier counterpart indicating more integration of the cortical network. Influence of basal ganglia and cerebellum was measured using eigenvector centrality. Results correlated with decreases and increases in cortical modularity respectively, with only the basal ganglia influence preceding cortical integration. Our results support the theory the basal ganglia shifts cortical networks to integrated states due to environmental demand. Cerebellar influence correlates with shifts to segregated cortical states, though may not play a causal role. © 2024, CC BY-NC-SA.

关键词： Integration

Narrowing of the Racial Disparities Gap in Survival of Patients With Mycosis Fungoides: A Longitudinal Analysis of the SEER database

学校读者我要写书评

暂无评论

Clinical Lymphoma, Myeloma and Leukemia 2025年第7期25卷 e501-e506页

作者： Le, Britney Soror, Noha Ismail, Hamid D. Baker, Mohammed Shetayyah, Salman Abu Chung, Catherine G. William, Basem M. Ohio University Heritage College of Osteopathic Medicine Dublin OH The University of Oklahoma College of Medicine Oklahoma City OK United States Department of Computational Data Science and Engineering North Carolina Agricultural and Technical State University Greensboro NC United States Faculty of Medicine Jordan University of Science and Technology Irbid Jordan The Ohio State University Comprehensive Cancer Center: Arthur G. James Cancer Hospital and Richard J. Solove Research Institute Division of Dermatology Columbus OH Ohio Health Blood and Marrow Transplant Program Columbus OH

Background: Mycosis fungoides (MF) is the commonest subtype of cutaneous T-cell lymphoma. In the United States, prior studies reported that African Americans (AA) with MF had poor outcomes. data characterizing differences in racial disparity outcomes over time are limited. Patients and Methods: We collected data from the United States Surveillance, Epidemiology, and End Results (SEER) database to investigate the survival patterns of patients with MF from 1988 to 2011. Cases were divided into 3 cohorts based on the year of diagnosis. Univariable and multivariable analysis were conducted to assess for factors associated with overall survival (OS). Results: 2896 cases of MF were detected, with a median follow-up duration of 60 months. The disparity in survival between the years 1988-1995 and 2004-2011 was significant (P = .05). The parameter estimates of the Cox proportional hazards model for the 1988-1995 period (using the 2004-2011 period as a reference) was also significant (P = .024). Patients diagnosed between 1988 and 1995 were 1.4 times more likely to die from the disease than those diagnosed between 2004 and 2011. The survival gap between AA and white patients narrowed in 1996-2003 and 2004-2011 in comparison to 1988-1995. This indicates improvements in the survival of AA patients over time. Conversely, the survival rates of white patients remained relatively stable over time. Conclusions: Our study demonstrates that AA with MF have reduced survival. Despite the persistent pattern of lower survival across all periods, the gap in survival between white and AA seems to be narrowing over time. © 2025 Elsevier Inc.

关键词： Cutaneous lymphoma Mycosis fungoides Outcome research Racial disparity SEER database

COVID-19 detection in computed tomography images with 2D and 3D approaches

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Ali Ahmed, Sara Atito Can Yavuz, Mehmet Umut Sen, Mehmet Gulsen, Fatih Tutar, Onur Korkmazer, Bora Samancı, Cesur Şirolu, Sabri Hamid, Rauf Eryürekli, Ali Ergun Mammadov, Toghrul Yanikoglu, Berrin Sabanci University Istanbul34956 Turkey Urbanstat The Istanbul University-Cerrahpaşa Cerrahpaşa Faculty of Medicine Turkey The Computer Science and Engineering Program Sabanci University Istanbul34956 Turkey The Sabanci University Center of Excellence in Data Analytics

Detecting COVID-19 in computed tomography (CT) or radiography images has been proposed as a supplement to the definitive RT-PCR test. We present a deep learning ensemble for detecting COVID-19 infection, combining slice-based (2D) and volume-based (3D) approaches. The 2D system detects the infection on each CT slice independently, combining them to obtain the patient-level decision via different methods (averaging and long-short term memory networks). The 3D system takes the whole CT volume to arrive to the patient-level decision in one step. A new high resolution chest CT scan dataset, called the IST-C dataset, is also collected in this work. The proposed ensemble, called IST-CovNet, obtains 90.80% accuracy and 0.95 AUC score overall on the IST-C dataset in detecting COVID-19 among normal controls and other types of lung pathologies;and 93.69% accuracy and 0.99 AUC score on the publicly available MosMed dataset that consists of COVID-19 scans and normal controls only.. The system is deployed at Istanbul University Cerrahpaşa School of Medicine. Copyright © 2021, The Authors. All rights reserved.

关键词： Computerized tomography

Accuracy of a one-dimensional reduction of dynamical systems on networks

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Kundu, Prosenjit Kori, Hiroshi Masuda, Naoki Department of Mathematics State University of New York BuffaloNY14260-2900 United States Department of Complexity Science and Engineering The University of Tokyo Chiba277-8561 Japan Computational and Data-Enabled Science and Engineering Program State University of New York at Buffalo BuffaloNY14260-5030 United States

Resilience is an ability of a system with which the system can adjust its activity to maintain its functionality when it is perturbed. To study resilience of dynamics on networks, Gao et al. [Nature, 530, 307 (2016)] proposed a theoretical framework to reduce dynamical systems on networks, which are high dimensional in general, to one-dimensional dynamical systems. The accuracy of this one-dimensional reduction relies on several assumption in addition to the assumption that the network has a negligible degree correlation. In the present study, we analyze the accuracy of the one-dimensional reduction assuming networks without degree correlation. We do so mainly through examining the validity of the individual assumptions underlying the method. Across five dynamical system models, we find that the accuracy of the one-dimensional reduction hinges on the spread of the equilibrium value of the state variable across the nodes in most cases. Specifically, the one-dimensional reduction tends to be accurate when the dispersion of the node's state is small. We also find that the correlation between the node's state and the node's degree, which is common for various dynamical systems on networks, is unrelated to the accuracy of the one-dimensional reduction. © 2021, CC BY.

关键词： Dynamical systems

Graph Laplacian Learning with Exponential Family Noise

学校读者我要写书评

暂无评论

IEEE Transactions on Signal and Information Processing over Networks 2025年

作者： Shi, Changhao Mishne, Gal UC San Diego Electrical and Computer Engineering Department CA92093 United States UC San Diego Hal.c.o.glu Data Science Institute and the Neurosciences Graduate Program CA92093 United States

Graph signal processing (GSP) is a prominent framework for analyzing signals on non-Euclidean domains. The graph Fourier transform (GFT) uses the combinatorial graph Laplacian matrix to reveal the spectral decomposition of signals in the graph frequency domain. However, a common challenge in applying GSP methods is that in many scenarios the underlying graph of a system is unknown. A solution in such cases is to construct the unobserved graph from available data, which is commonly referred to as graph or network inference. Although different graph inference methods exist, they are restricted to learning from either smooth graph signals or simple additive Gaussian noise. Other types of noisy data, such as discrete counts or binary digits, are rather common in real-world applications, yet are underexplored in graph inference. In this paper, we propose a versatile graph inference framework for learning from graph signals corrupted by exponential family noise. Our framework generalizes previous methods from continuous smooth graph signals to various data types. We propose an alternating algorithm that jointly estimates the graph Laplacian and the unobserved smooth representation from the noisy signals. We also extend our approach to include an offset variable which models different levels of variation of the nodes. Since real-world graph signals are frequently non-independent and temporally correlated, we further adapt our original setting to a timevertex formulation. We demonstrate on synthetic and real-world data that our new algorithms outperform competing Laplacian estimation methods that suffer from noise model mismatch. © 2025 IEEE.

关键词： Laplace transforms

Biomedical data and AI

学校读者我要写书评

暂无评论

science China Life sciences 2025年第5期68卷 1536-1540页

作者： Hao Xu Shibo Zhou Zefeng Zhu Vincenzo Vitelli Liangyi Chen Ziwei Dai Ning Yang Luhua Lai Shengyong Yang Sergey Ovchinnikov Zhuoran Qiao Sirui Liu Chen Song Jianfeng Pei Han Wen Jianfeng Feng Yaoyao Zhang Zhengwei Xie Yang-Yu Liu Zhiyuan Li Fulai Jin Hao Li Mohammad Lotfollahi Xuegong Zhang Ge Yang Shihua Zhang Ge Gao Pulin Li Qi Liu Jing-Dong Jackie Han Peking-Tsinghua Center for Life Sciences (CLS) Academy for Advanced Interdisciplinary StudiesPeking University Center for Quantitative Biology (CQB) Academy for Advanced Interdisciplinary StudiesPeking University Peking University-Tsinghua University-National Institute of Biological Sciences Joint Graduate Program Academy for Advanced Interdisciplinary StudiesPeking University Department of Physics University of Chicago School of Life Sciences Southern University of Science and Technology Peking University Chengdu Academy for Advanced Interdisciplinary Biotechnologies College of Chemistry and Molecular Engineering Peking University Department of Biotherapy Cancer Center and State Key Laboratory of BiotherapyWest China HospitalSichuan University Department of Biology Massachusetts Institute of Technology Lambic Therapeutics Inc. Changping Laboratory Al for Science Institute Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence Fudan University Department of Obstetrics and Gynecology West China Second University HospitalSichuan University Peking University International Cancer Institute and Peking University-Yunnan Baiyao International Medical Institute and State Key Laboratory of Natural and Biomimetic Drugs Department of Molecular and Cellular PharmacologySchool of Pharmaceutical SciencesPeking University Health Science CenterPeking University Channing Division of Network Medicine Department of MedicineBrigham and Women's Hospital and Harvard Medical School Center for Artificial Intelligence and Modeling the Carl R.Woese Institute for Genomic BiologyUniversity of Illinois Urbana-Champaign Department of Genetics and Genome Sciences School of Medicine and Department of Computer and Data Sciences and Department of Population and Quantitative Health SciencesCase Western Reserve University Department of Biochemistry and Biophysics University of California Sanger Institute Department of Automation Tsinghua University State Key Laboratory of Multimodal Artificial Intelligence Systems I

The development of artificial intelligence(AI) and the mining of biomedical data complement each other. From the direct use of computer vision results to analyze medical images for disease screening, to now integrating biological knowledge into models and even accelerating the development of new AI based on biological discoveries, the boundaries of both are constantly expanding, and their connections are becoming closer.

关键词：